Comment by r0s
6 days ago
Weird to claim the llm does all the boring learning and boilerplate for you as a selling point, but then also insist we still need to responsibly read all the output, and if you can't understand it's a "skill issue".
Also the emphasis on greenfield projects? Starting is by FAR the easiest part. That's not impressive to me. When do we get to code greenfield for important systems? Reminds me of the equally absurd example of language choice. You think you get to choose? What?
Imagine all the code these agents are going to pump out that can never be reviewed in a reasonable time frame. The noise generated at the whim of bike-shedding vibe coders is going to drown all the senior reviewers soon enough. I'll call that Cowboy Coders on Steroids. Anyone with skills will be buried in reviews, won't have time for anything else, and I predict stricter code gen policies to compensate.
I don't have a huge dog in this fight apart from AI advocates being annoying... but I would say that for greenfield projects the interesting thing is that I can get a skeleton of a working iOS app for something simple in like an hour of some copy/pasting stuff from ChatGPT. Instead of spending a good amount of time trying to get through learning material to do it.
It's nice to build throwaway things _so fast_, especially in the sort of fuzzy stuff like frontend where it's fine for it to be completely wrong. And then I can just use my own sense of how computers work to fix up what I care about, delete a bunch of what I don't care about... It's pretty amazing.
For existing projects I have only witnessed garbage output. I know people have success. I haven't seen it.
I have witnessed PMs taking a bullet pointed list of requirements and then use ChatGPT to generate paragraphs of text for some reason. You had the list!
And (rigorously) reviewing code is easily 10x harder than writing it.
But this won't stop it from happening.
This is just obviously not true. I had a full-time job of reviewing code for roughly 15 years and it was never true, but it's also just intuitively not true that engineers spend 10 hours reviewing their peers code to every 1 they spend writing it.
What you mean to claim here is that verification is 10x harder than authorship. That's true, but unhelpful to skeptics, because LLMs are extremely useful for verification.
I once graded over 100 exams in an introductory programming course (Python). The main exercise was to implement a simple game (without using a runtime).
Some answers were trivial to grade—either obviously correct or clearly wrong. The rest were painful and exhausting to evaluate.
Checking whether the code was correct and tracing it step by step in my head was so draining that I swore never to grade programming again.
7 replies →
While I'm still a skeptic (despite my Cursor usage at work), I still absolutely agree. Careful review has never been 10x more difficult than writing the code, I'm not sure where this comes from. And I've had about the same experience as you.
Also, and know this doesn't matter, but it's so weird to see this downvoted. That's not an "I disagree" button...
4 replies →
I really don't think that's true at all. Anyone here can read and sign off on 1000 lines of code faster than they can write the same 1000 lines of code, pretty much no matter what the code is.
It also depends heavily on the language.
I can review 100x more Go code in a set amount of time than I can, say React.
With Go there are repetitive structures (if err == nil) and not that many keywords, it's easy to sniff out the suspicious bits and focus on them.
With Javascript and all of the useWhatevers and cyclic dependencies and functions returning functions that call functions, it's a lot harder to figure out what the code does just by reading it.
1 reply →
You have misunderstood this "common wisdom".
The idea is that people will spend 10x more time reading your code in all future time stacked together. Not that reading and understanding your code once takes 10x the effort of writing it, which is obviously untrue.
Here is the quote from Clean Code, where this idea seems to originate from:
> Indeed, the ratio of time spent reading versus writing code is well over 10 to 1.
I think the point is that the person orchestrating the agent(s) reviews the code. It doesn't make sense to have 5 Juniors using agents to submit PRs and a senior or two reviewing it all. You just have the senior(s) orchestrating agents and reviewing it themselves. Maybe one or two juniors because we still need to train new devs, but maybe the junior doesn't even use an LLM. Maybe the junior writes code manually so they can learn programming properly before they start being an "AI lead".
Everyone is still responsible for the code they produce. I review my own PRs before I expect others to, and I don't even use AI. I think what the article describes seems interesting though.
Yeah, I remember five years ago (before being sold this latest VC crock of bull) when reviewing shitty thoughtless code was the tedious and soul-sucking part of programming.